This research prepares an automatic pipeline for generating reliable question-answer (Q&A) tests using AI chatbots. We automatically generated a GPT-4o-mini-based Q&A test for a Natural Language Processing course and evaluated its psychometric and perceived-quality metrics with students and experts. A mixed-format IRT analysis showed that the generated items exhibit strong discrimination and appropriate difficulty, while student and expert star ratings reflect high overall quality. A uniform DIF check identified two items for review. These findings demonstrate that LLM-generated assessments can match human-authored tests in psychometric performance and user satisfaction, illustrating a scalable approach to AI-assisted assessment development.
@article{arxiv.2505.06591,
title = {Evaluating LLM-Generated Q&A Test: a Student-Centered Study},
author = {Anna Wróblewska and Bartosz Grabek and Jakub Świstak and Daniel Dan},
journal= {arXiv preprint arXiv:2505.06591},
year = {2025}
}